eprintid: 11066 rev_number: 8 eprint_status: archive userid: 2 dir: disk0/00/01/10/66 datestamp: 2024-02-29 23:30:20 lastmod: 2024-02-29 23:30:21 status_changed: 2024-02-29 23:30:20 type: article metadata_visibility: show creators_name: Kader, Mohammed Abdul creators_name: Ullah, Muhammad Ahsan creators_name: Islam, Md Saiful creators_name: Ferriol Sánchez, Fermín creators_name: Samad, Md Abdus creators_name: Ashraf, Imran creators_id: creators_id: creators_id: creators_id: fermin.ferriol@unini.edu.mx creators_id: creators_id: title: A real-time air-writing model to recognize Bengali characters ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: uninipr_produccion_cientifica full_text_status: public keywords: air-writing; Bengali character; human-computer interaction; hand gestures; machine learning abstract: Air-writing is a widely used technique for writing arbitrary characters or numbers in the air. In this study, a data collection technique was developed to collect hand motion data for Bengali air-writing, and a motion sensor-based data set was prepared. The feature set as then utilized to determine the most effective machine learning (ML) model among the existing well-known supervised machine learning models to classify Bengali characters from air-written data. Our results showed that medium Gaussian SVM had the highest accuracy (96.5%) in the classification of Bengali character from air writing data. In addition, the proposed system achieved over 81% accuracy in real-time classification. The comparison with other studies showed that the existing supervised ML models predicted the created data set more accurately than many other models that have been suggested for other languages. date: 2024-02 publication: AIMS Mathematics volume: 9 number: 3 pagerange: 6668-6698 id_number: doi:10.3934/math.2024325 refereed: TRUE issn: 2473-6988 official_url: http://doi.org/10.3934/math.2024325 access: open language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Abierto Inglés Air-writing is a widely used technique for writing arbitrary characters or numbers in the air. In this study, a data collection technique was developed to collect hand motion data for Bengali air-writing, and a motion sensor-based data set was prepared. The feature set as then utilized to determine the most effective machine learning (ML) model among the existing well-known supervised machine learning models to classify Bengali characters from air-written data. Our results showed that medium Gaussian SVM had the highest accuracy (96.5%) in the classification of Bengali character from air writing data. In addition, the proposed system achieved over 81% accuracy in real-time classification. The comparison with other studies showed that the existing supervised ML models predicted the created data set more accurately than many other models that have been suggested for other languages. metadata Kader, Mohammed Abdul; Ullah, Muhammad Ahsan; Islam, Md Saiful; Ferriol Sánchez, Fermín; Samad, Md Abdus y Ashraf, Imran mail SIN ESPECIFICAR, SIN ESPECIFICAR, SIN ESPECIFICAR, fermin.ferriol@unini.edu.mx, SIN ESPECIFICAR, SIN ESPECIFICAR (2024) A real-time air-writing model to recognize Bengali characters. AIMS Mathematics, 9 (3). pp. 6668-6698. ISSN 2473-6988 document_url: http://repositorio.unib.org/id/eprint/11066/1/10.3934_math.2024325.pdf